JointOnlineLearningandDecision-MakingviaDualMirrorDescentAlfonsoLobos1PaulGrigas1ZhengWen2Abstractensuringthatwedonotincurtoomanycoststooearly,(ii)ensuringthatenoughcostsareincurredtomeetthelowerWe...
Decision-MakingUnderSelectiveLabels:OptimalFinite-DomainPoliciesandBeyondDennisWei1Abstracttoobserveitifbailisdenied.Inhiring,acandidate’sjobperformanceisobservedonlyiftheyarehired.Selectivelabels...
CooperativeMulti-AgentBanditswithHeavyTailsAbhimanyuDubey1AlexPentland1AbstractAv,t∈A,wherethespaceofactionsAisassumedtobefiniteandcountable(A=K).Itthenobtainsani.i.d.Westudytheheavy-tailedstochas...
DecentralizedReinforcementLearning:GlobalDecision-MakingviaLocalEconomicTransactionsMichaelChang1SidhantKaushik1S.MatthewWeinberg2ThomasL.Griffiths2SergeyLevine1Abstract1.IntroductionThispaperseeks...
DecisionTreesforDecision-MakingunderthePredict-then-OptimizeFrameworkAdamN.Elmachtoub1JasonCheukNamLiang2RyanMcNellis13Abstract1.IntroductionWeconsidertheuseofdecisiontreesforManyDecision-Makingpro...
ActiveLearningforDecision-MakingfromImbalancedObservationalDataIirisSundin1PeterSchulam2EeroSiivola1AkiVehtari1SuchiSaria2SamuelKaski1Abstractdecision,x.Then,thegoalistoestimatep(YX=x,A=a)and,furth...
